Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jstoup111/ai-conductor --skill conflict-checkgit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jstoup111/ai-conductor/conflict-check)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/conflict-check"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/conflict-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/conflict-check"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/conflict-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 274 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 286 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.03404 |
| Opus 5 | $0.00026 | $0.01702 |
| Sonnet 5 | $0.00010 | $0.00681 |
| Haiku 4.5 | $0.00005 | $0.00340 |
Grade A, and why
conflict-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Detects when new stories contradict, overlap, or create impossible states with existing ones. Provides guided resolution so conflicts are resolved before implementation begins — preventing the expensive discovery of contradictions during or after coding.
Correctness gate: "these two stories conflict" (or "clean") is a judgment call. Per the
/verify-claims protocol, ground each asserted conflict in the specific contradicting text with a
confidence %, and do not declare a clean pass on the assumption that two stories are compatible
when their interaction was never actually reasoned through — an unexamined pair is not a verified
clean pass.
Practices
1. Inventory
Load ALL stories and specs:
- All files in
.docs/stories/(existing + newly written) - Active specs from
.docs/specs/(for design-level context) - Approved ADRs from
.docs/decisions/(as selected below) - Previous conflict reports from
.docs/conflicts/(to check for recurring patterns)
Read conflict_check.adr_corpus; if it is unset, use change_set.
change_set— load the approved ADRs in the current spec's change set. This is the default corpus. Do not narrow it or parse supersession status.repo_wide— load all approved ADRs, narrow the corpus to ADRs whose subject overlaps the current spec's stories, and record both the examined and narrowed-out ADRs in the conflict report. Apply supersession-status parsing only at this scope: exclude an ADR only when it is unambiguously fully superseded; retain an ADR with a partial or ambiguous supersession because its remaining decision may still conflict with a story.
1b. As-Built Story Handling
When stories have [AS-BUILT] markers (from /bootstrap), they document existing working
code. Overlap between as-built stories is expected — the same endpoint may appear in multiple
stories describing different aspects of the same feature.
Scoring adjustment for as-built pairs:
- Two
[AS-BUILT]stories sharing an endpoint → not a conflict unless they assert contradictory behavior. Same endpoint, same behavior, different story angle = normal. [AS-BUILT]vs new story → check normally. New work may genuinely conflict with existing behavior.- Two new stories → check normally.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 315 lines · 52 tokens per session scan A 97a57ae00285
conflict-check is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 3,404 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…